COMPMID-1761: NEON: Implement Pack

Change-Id: Icc3392494b1e3361e8fd925da200827c494351b3
Reviewed-on: https://review.mlplatform.org/430
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLStackLayer.h b/arm_compute/runtime/CL/functions/CLStackLayer.h
index 9794014..5b821b8 100644
--- a/arm_compute/runtime/CL/functions/CLStackLayer.h
+++ b/arm_compute/runtime/CL/functions/CLStackLayer.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018 ARM Limited.
+ * Copyright (c) 2018-2019 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -48,13 +48,17 @@
     CLStackLayer();
     /** Initialise the kernel's inputs vector and output.
      *
+     * @note Supported input tensor rank: up to 4
+     *
      * @param[in]  input  The vectors containing all the tensors with the same shape to stack. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
      * @param[in]  axis   The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
      *                    Negative values wrap around
      * @param[out] output Output tensor. Data types supported: Same as @p input.
      */
     void configure(const std::vector<ICLTensor *> &input, int axis, ICLTensor *output);
-    /** Static function to check if given info will lead to a valid configuration of @ref CLDepthConcatenateLayer
+    /** Static function to check if given info will lead to a valid configuration of @ref CLStackLayerKernel
+     *
+     * @note Supported input tensor rank: up to 4
      *
      * @param[in] input  The vectors containing all the tensors info with the same shape to stack. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
      * @param[in] axis   The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
@@ -73,5 +77,5 @@
     std::unique_ptr<CLStackLayerKernel[]> _stack_kernels;
     unsigned int                          _num_inputs;
 };
-}
+} // namespace arm_compute
 #endif /* __ARM_COMPUTE_CLSTACKLAYER_H__ */
diff --git a/arm_compute/runtime/NEON/NEFunctions.h b/arm_compute/runtime/NEON/NEFunctions.h
index 2daef70..da61853 100644
--- a/arm_compute/runtime/NEON/NEFunctions.h
+++ b/arm_compute/runtime/NEON/NEFunctions.h
@@ -123,6 +123,7 @@
 #include "arm_compute/runtime/NEON/functions/NESobel7x7.h"
 #include "arm_compute/runtime/NEON/functions/NESoftmaxLayer.h"
 #include "arm_compute/runtime/NEON/functions/NESplit.h"
+#include "arm_compute/runtime/NEON/functions/NEStackLayer.h"
 #include "arm_compute/runtime/NEON/functions/NEStridedSlice.h"
 #include "arm_compute/runtime/NEON/functions/NETableLookup.h"
 #include "arm_compute/runtime/NEON/functions/NEThreshold.h"
diff --git a/arm_compute/runtime/NEON/functions/NEStackLayer.h b/arm_compute/runtime/NEON/functions/NEStackLayer.h
new file mode 100644
index 0000000..6032dae
--- /dev/null
+++ b/arm_compute/runtime/NEON/functions/NEStackLayer.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright (c) 2018-2019 ARM Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __ARM_COMPUTE_NESTACKLAYER_H__
+#define __ARM_COMPUTE_NESTACKLAYER_H__
+
+#include "arm_compute/core/Types.h"
+#include "arm_compute/runtime/IFunction.h"
+
+#include "arm_compute/core/NEON/kernels/NEStackLayerKernel.h"
+
+#include <memory>
+#include <vector>
+
+namespace arm_compute
+{
+class ITensor;
+
+/** Basic function to stack tensors along an axis. This function calls the following kernel:
+ *
+ * -# @ref NEStackLayerKernel
+ *
+ */
+class NEStackLayer : public IFunction
+{
+public:
+    /** Default constructor */
+    NEStackLayer();
+    /** Initialise the kernel's inputs vector and output.
+     *
+     * @note Supported input tensor rank: up to 4
+     *
+     * @param[in]  input  The vectors containing all the tensors with the same shape to stack. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
+     * @param[in]  axis   The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
+     *                    Negative values wrap around
+     * @param[out] output Output tensor. Data types supported: Same as @p input.
+     */
+    void configure(const std::vector<ITensor *> &input, int axis, ITensor *output);
+    /** Static function to check if given info will lead to a valid configuration of @ref NEStackLayerKernel
+     *
+     * @note Supported input tensor rank: up to 4
+     *
+     * @param[in] input  The vectors containing all the tensors info with the same shape to stack. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
+     * @param[in] axis   The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
+     *                   Negative values wrap around
+     * @param[in] output Output tensor info. Data types supported: Same as @p input.
+     *
+     * @return a status
+     */
+    static Status validate(const std::vector<ITensorInfo *> &input, int axis, const ITensorInfo *output);
+
+    // Inherited methods overridden:
+    void run() override;
+
+private:
+    std::vector<ITensor *>                _input;
+    std::unique_ptr<NEStackLayerKernel[]> _stack_kernels;
+    unsigned int                          _num_inputs;
+};
+} // namespace arm_compute
+#endif /* __ARM_COMPUTE_NESTACKLAYER_H__ */